The role of inference in AI: Start S.M.A.L.L. with mindful modeling

This chapter explores trustworthiness in AI and penetrates the black-box opacity through explainable, fair, and ethical AI solutions. AI remains a spirited topic within academic, government, and industrial literature. Much has occurred since the last AI winter in the early 1990's;yet, numerous sources indicate the initial successes solving problems like computer vision, speech recognition, and natural sciences may wane — plunging AI into another winter. Many factors contributed to advances in AI: more data science courses in universities producing data-science capable graduates, high venture capital funding levels encouraging startups, and a decade of broadening awareness among corporate executives about AI promises, real or perceived. Nonetheless, could sources like Gartner be right? Are we approaching another AI winter? As the world learned during the COVID-19 pandemic, when we find ourselves in a crisis, focusing on the fundamentals can have a powerful effect to easing the troubles. As AI makes history, it relies on progress from other domains such as data availability, computing power, and algorithmic advances. Balance among elements maintains a healthy system. AI is no different. Too much or too little of any elemental capability can slow down overall progress. This chapter integrates fundamental ideas from psychology (heuristics and bias), mindfulness in modeling (conceptual models in group settings), and inference (both classical and contemporary). Practitioners may find the techniques proposed in this chapter useful next steps in AI evolution aimed at understanding human behavior. The techniques we discuss can protect against negative impacts resulting from a future AI winter through proper preparation: appreciating the fundamentals, understanding AI assumptions and limitations, and approaching AI assurance in a mindful manner as it evolves. This chapter will address the fundamentals in a unifying example focused on healthcare, with opportunities for trustworthy AI that is impartial, fair, and unbiased. © 2023 Elsevier Inc. All rights reserved.

Diagnostic Errors in Japanese Community Hospitals and Related Factors: A Retrospective Cohort Study.

Diagnostic error has recently become a crucial clinical problem and an area of intense research. However, the reality of diagnostic errors in regional hospitals remains unknown. This study aimed to clarify the reality of diagnostic errors in regional hospitals in Japan. A 10-month retrospective cohort study was conducted from January to October 2021 at the emergency room of Oda Municipal Hospital in central Shimane Prefecture, Japan. Participants were divided into groups with or without diagnostic errors, and independent variables of patient, physician, and environmental factors were analyzed using Fisher's exact test, univariate (Student's t-test and Welch's t-test), and logistic regression analyses. Diagnostic errors accounted for 13.1% of all eligible cases. Remarkably, the proportion of patients treated without oxygen support and the proportion of male patients were significantly higher in the group with diagnostic errors. Sex bias was present. Additionally, cognitive bias, a major factor in diagnostic errors, may have occurred in patients who did not require oxygen support. Numerous factors contribute to diagnostic errors; however, it is important to understand the trends in the setting of each healthcare facility and plan and implement individualized countermeasures.

Decision Challenges for Managing Acute Paediatric Infections: Implications for Antimicrobial Resistance.

Overprescribing of antibiotics in paediatrics accounts for a significant proportion of inappropriate antibiotic use in human healthcare, thereby contributing to the global health emergency of antimicrobial resistance. Antimicrobial stewardship efforts are complicated by the unique social dynamics in paediatric healthcare, with a specific challenge being the prominent role of parents and carers who act as intermediaries between prescribers and paediatric patients. In this Perspective article concentrating on healthcare of the United Kingdom, we describe this complicated interplay of different decision stakeholders (patients, parents and prescribers), outline four dimensions of decision challenges (social, psychological, systemic and specific diagnostic and treatment challenges) and provide a number of theory-based strategies for supporting different stakeholders during the decision process, ultimately with the aim of improving antimicrobial stewardship. Key decision challenges for patients and carers include limited knowledge and experience of managing infections, which were exacerbated during the COVID-19 pandemic and frequently result in health anxiety and inappropriate health-seeking behaviours. Challenges for medical prescribers span societal pressures from prominent patient litigation cases, cognitive biases, and system pressures to specific diagnostic problems (e.g., age limitations of current clinical scoring systems). Strategies for mitigating decision challenges in paediatric infection management will need to include a range of context- and stakeholder-specific actions, including improvements of integrated care and public health education as well as better clinical decision tools and access to evidence-based guidelines.

Cognitive bias in the context of epidemic

In connection with the scope and duration of the COVID-19 pandemic, the clinical judgement of clinicians and medical practitioners could be influenced such that diagnostic errors (delays and inaccuracies) may ensue. We hereby recall through two clinical scenarios the constant need for practitioners to take a step back in reflecting of the diagnostic process to avoid the <<tunnel effect>> which may result in delaying common and frequent infectious diseases. The flu-like symptoms presented by these patients (fever, myalgia and asthenia...) quickly prompted our emergency room colleagues to suspect SARS-CoV-2 infection. However, further investigations including imagery and blood cultures revealed completely different but common infectious disease conditions, which are potentially fatal.Copyright © 2020 Editions Medecine et Hygiene. All rights reserved.

A Rare Cause of Enteritis in an Adult Male

Introduction: IgA vasculitis is more commonly seen in the pediatric population than in adults. Rarely IgA vasculitis is associated with malignancy, most commonly solid tumor malignancies, although there are case reports of association with hematologic malignancies. We report a case of large B-cell lymphoma mimicking IgA vasculitis in a 33-year-old immunosuppressed male with a prior history of IgA vasculitis. Case Description/Methods: A 33-year-old Caucasian male post renal transplant from reflux nephropathy on chronic immunosuppression was hospitalized for postprandial epigastric abdominal pain, nausea, vomiting and diarrhea. Two years prior, he was admitted for the same symptoms, palpable purpura of the lower extremities and elevated serum IgA. Enteroscopy had shown duodenal and jejunal ulceration with biopsies staining positive for IgA, confirming IgA vasculitis. He had complete resolution with a steroid taper. His current presentation had resulted in multiple hospital admissions, but empiric trial of steroids failed to alleviate symptoms. Vitals were normal and exam was notable for epigastric tenderness. Labs were notable for WBC 19.00 x103/cmm with normal differential, hemoglobin 9.2 gm/dL (prior 11.0 gm/dL), CRP 20.7 mg/L, serum creatinine 2.7 mg/dL (prior 1.5 mg/dL), and urinalysis with proteinuria, sterile pyuria, and hematuria. CTA abdomen/pelvis revealed thickening of the duodenum with shotty mesenteric lymph nodes without ischemia. Enteroscopy revealed an erythematous duodenum and jejunum (figure A). Jejunal biopsy (figure B) revealed CD20 positive cells consistent with DLCBL (figure C). He was seen by oncology and treated with R-CHOP but later unfortunately expired due to COVID-19 complications. Discussion(s): Non small cell lung cancer and renal cell carcinoma are most commonly associated with IgA vasculitis. It may also be seen in both Hodgkin and Non-Hodgkin lymphomas in adult patients. If IgA vasculitis occurs after a malignancy is diagnosed, it may indicate that metastasis has occurred. Malignancy associated IgA vasculitis is more likely to have an incomplete response to steroids and requires treatment of the underlying malignancy to achieve remission. Our case illustrates posterior probability error and premature closure cognitive biases. We should consider alternative diagnoses rather than anchor on prior diagnoses even when presentations are similar. Our case also highlights the importance of considering occult malignancy in adults with diagnosis of IgA vasculitis.

Vaccine hesitancy, refusal, Covid-19 and cognitive bias: a narrative review

Context. Vaccine hesitancy, defined as "delaying or refusing safe vaccination despite its availability", has been classified as one of the 10 health threats by WHO. The main reasons for vaccine hesitancy in Covid-19 are the dangerousness of the vaccine, the opposition to vaccination in general, and a virus that is considered not very dangerous. Errors resulting from subconscious mental procedures of information processing, called cognitive biases, participate in the decision to be vaccinated. Objective. The objective of this work was to describe the cognitive biases that may participate in vaccine hesitation in Covid-19 and its refusal. Methods. Narrative review of the literature according to PRISMA criteria, from 2011 to 2021 on Medline((R)) and Cairn((R)), and from references. Results. Ten reviews or position papers were selected. Availability bias (media coverage of an adverse event), representativeness bias (stereotype rather than statistical), attribution bias (anecdotal observation and causality) may participate in the judgment of vaccine dangerousness. Ambiguity aversion, omission and present bias may partly explain the inaction choice of some health care users. Distancing from power leads to distrust of public authorities. This feeling of inequality contributes to the opposition to vaccination in general. The biases of naturalness (natural immunization) and optimism contribute to the judgment of a virus that is not very dangerous. Conclusion. Motivational interviewing of patients with vaccine hesitation or refusal can be facilitated by the knowledge of these biases.

The relationship between the psychological distress derived from COVID-19 and the loss aversion is modulated by the alexithymia trait

studies on stress and decision-making usually address acute and artificial stressors. However, COVID-19 outbreak set the perfect scena-rio to address how decision-making, and specifically loss aversion, could be affected by a real and persistent stressor, able to promote a significant psychological distress. In parallel, alexithymia has been identified as a potential moderator of the loss aversion expression, since it could impair the incorporation of emotional information when making a decision, leading to "cold" decisions. Through a within-subjects design (N = 70), our aim was to study the relationship between the psychological distress caused by the pandemic context and the loss aversion changes, considering alexithymia as a moderating factor. Our results show a significant increment in both psychological distress and loss aversion, merely one month after the confinement's onset. Moreover, both variables were positively associated only when alexithymia was low, i.e., the alexithymia buffered the effect of psychological distress on decision-making: a higher alexithymia implied a lower loss aversion increase.

COVID-19 vaccine hesitancy is associated with beliefs on the origin of the novel coronavirus in the UK and Turkey.

BACKGROUND: Much research effort is focused on developing an effective vaccine for combatting coronavirus disease 2019 (COVID-19). Vaccine development itself, however, will not be enough given that a sufficient amount of people will need to be vaccinated for widespread immunity. Vaccine hesitancy is on the rise, varies across countries, and is associated with conspiratorial worldview. Given the rise in COVID-19-related conspiracy theories, we aimed to examine the levels of COVID-19 vaccine hesitancy and its association with beliefs on the origin of the novel coronavirus in a cross-cultural study. METHODS: We conducted an online survey in the UK (N = 1088) and Turkey (N = 3936), and gathered information on participants' willingness to vaccinate for a potential COVID-19 vaccine, beliefs on the origin of the novel coronavirus, and several behavioural and demographic predictors (such as anxiety, risk perception, government satisfaction levels) that influence vaccination and origin beliefs. RESULTS: In all, 31% of the participants in Turkey and 14% in the UK were unsure about getting themselves vaccinated for a COVID-19 vaccine. In both countries, 3% of the participants rejected to be vaccinated. Also, 54% of the participants in Turkey and 63% in the UK believed in the natural origin of the novel coronavirus. Believing in the natural origin significantly increased the odds of COVID-19 vaccine acceptance. CONCLUSIONS: Our results point at a concerning level of COVID-19 vaccine hesitancy, especially in Turkey, and suggest that wider communication of the scientific consensus on the origin of the novel coronavirus with the public may help future campaigns targeting COVID-19 vaccine hesitancy.

Impact of COVID-19 pandemic on the clinical reasoning of the physicians.

We report the case of a 65-year-old patient who was admitted during the COVID-19 pandemic to the intensive care unit for acute respiratory distress. Following a large meal the day before, she had recurrent episodes of vomiting, which were followed by intense retrosternal pain with progressively worsening dyspnea. The patient was admitted with initial suspicion of acute respiratory failure secondary to SARS-CoV-2 infection. However, after a careful anamnesis, the diagnosis of Boerhaave's syndrome was suggested. The aim of this article is to try to understand, through this clinical case of Boerhaave's syndrome, how this health crisis could influence the clinical reasoning of the physicians.Copyright © SRLF 2021.

Biased social comparison in the moment of crisis: The better-than-average effect and COVID-19

The better-than-average effect (BTAE) is a mechanism where people perceive oneself as better than others. The BTAE could be one of the phenomena explaining why people follow-in the moment of a global health crisis-guidelines ("I am superior to others, and I [will]) take extra precautions, e.g., a vaccine shot"). In this paper, we investigate the BTAE with 3,066 respondents. In Study 1, in all countries, across two measurements in time, the BTAE was present: Participants rated their involvement in self-protection as greater in comparison to others. Study 2 replicated this effect, proving its robustness. Participants estimated their willingness to vaccinate as higher than others. The BTAE was a significant predictor of willingness to vaccinate. (PsycInfo Database Record (c) 2023 APA, all rights reserved)

Diagnostic Bias in the COVID-19 Pandemic: A Series of Short Cases.

During the COVID-19 pandemic, healthcare systems have faced unprecedented pressures. One challenge has been to promptly recognise non-COVID-19 conditions. Cognitive bias due to the availability heuristic may cause difficulties in reaching the correct diagnosis. Confirmation bias may also affect imaging interpretation. We report three cases with an alternative final diagnosis in whom COVID-19 was initially suspected: (a) Pneumocystis jirovecii pneumonia with unrecognised HIV infection; (b) pulmonary lymphangitis carcinomatosis; and (c) ST elevation myocardial infarction causing acute pulmonary oedema. To help mitigate bias, there is no substitute for thoughtful clinical assessment and critical appraisal when evaluating new information and formulating the differential diagnosis. LEARNING POINTS: The availability heuristic during the recent pandemic may lead to cognitive bias in favour of COVID-19 diagnosis and delayed recognition of other conditions, especially in patients presenting with similar non-specific features.Confirmation bias towards COVID-19 can also affect the interpretation of pulmonary imaging which is central to the investigation of cases with suspected pneumonitis.Diagnostic bias can be mitigated by recognition and allowing time for a thorough clinical history and methodical examination of the patients.

Thinking disposition, thinking style, and susceptibility to causal illusion predict fake news discriminability

Acceptance of fake news is probably modulated by an intricate interplay of social, cultural, and political factors. In this study, we investigated whether individual-level cognitive factors related to thinking and decision making could influence the tendency to accept fake news. A group of volunteers responded to a COVID19-related fake news discrimination scale as well as to questionnaires assessing their thinking style (reflective vs. intuitive) and thinking disposition (actively open-mindedness). Furthermore, they completed a computerized contingency learning task aimed at measuring their tendency to develop a causal illusion, a cognitive bias leading to perceive causal connections between non-contingent events. More actively open-minded and more reflective individuals presented higher fake news discrimination scores. In addition, those who developed weaker causal illusions in the contingency learning task were also more accurate at differentiating between fake and legitimate news. Actively open-minded thinking was the main contributor in a regression model predicting fake news discrimination.Copyright © 2022 The Authors. Applied Cognitive Psychology published by John Wiley & Sons Ltd.

Desaturation during the pandemic: Covid or cognitive bias?

The coronavirus pandemic has put an unprecedented strain on our health care system. An urgent need for timely and accurate diagnosis coupled with an inordinate caseload and myriad overlapping signs and symptoms with other differentials is leaving physicians fatigued. This often leads to the use of mental shortcuts - "heuristics" by the strained mind and the inadvertent use of intuitive thought processes rather than the more controlled analytical thinking to cope and speed up the decision-making process. Availability bias - making a recent or vivid patient diagnosis more readily accessible to the mind - and anchoring bias - relying too heavily on a single symptom for deducing diagnosis - are among the most prevalent cognitive biases. Therefore, it is not unexpected that any new cases of acute onset respiratory illness may be mis-diagnosed as coronavirus disease 2019 during the pandemic, significantly impacting the morbidity and mortality of true diagnosis. To reduce the risk of patient harm, it is therefore imperative that medical practitioners be aware of the existence and influence of cognitive bias in clinical decision making and maintain sight of a variety of differential diagnoses to ensure that no adverse condition is overlooked.

Searching for the cognitive basis of anti-vaccination attitudes

Research on the reasons for vaccine hesitancy has largely focused on factors directly related to vaccines. In contrast, the present study focused on cognitive factors that are not conceptually related to vaccines but that have been linked to other epistemically suspect beliefs such as conspiracy theories and belief in fake news. This survey was conducted before the Covid-19 pandemic (N = 356). The results showed that anti-vaccination attitudes decreased slightly with cognitive abilities and analytic thinking styles, and strongly with scientific literacy. In addition, anti-vaccination attitudes increased slightly with teleological bias and strongly with an intuitive thinking style, ontological biases, and religious and paranormal beliefs. The results suggest that the same cognitive mechanisms that predispose to other epistemically suspect beliefs may predispose to anti-vaccination attitudes as well. The findings also indicate that pro-vaccination communication should focus on early prevention and that interventions against vaccine hesitancy should strive to be intuitively appealing. © 2022 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.

Using an experiential learning model to teach clinical reasoning theory and cognitive bias: an evaluation of a first-year medical student curriculum

BACKGROUND: Most medical students entering clerkships have limited understanding of clinical reasoning concepts. The value of teaching theories of clinical reasoning and cognitive biases to first-year medical students is unknown. This study aimed to evaluate the value of explicitly teaching clinical reasoning theory and cognitive bias to first-year medical students. METHODS: Using Kolb's experiential learning model, we introduced dual process theory, script theory, and cognitive biases in teaching clinical reasoning to first-year medical students at an academic medical center in New York City between January and June 2020. Due to the COVID-19 pandemic, instruction was transitioned to a distance learning format in March 2020. The curriculum included a series of written clinical reasoning examinations with facilitated small group discussions. Written self-assessments prompted each student to reflect on the experience, draw conclusions about their clinical reasoning, and plan for future encounters involving clinical reasoning. We evaluated the value of the curriculum using mixed-methods to analyze faculty assessments, student self-assessment questionnaires, and an end-of-curriculum anonymous questionnaire eliciting student feedback. RESULTS: Among 318 total examinations of 106 students, 254 (80%) had a complete problem representation, while 199 (63%) of problem representations were considered concise. The most common cognitive biases described by students in their clinical reasoning were anchoring bias, availability bias, and premature closure. Four major themes emerged as valuable outcomes of the CREs as identified by students: (1) synthesis of medical knowledge;(2) enhanced ability to generate differential diagnoses;(3) development of self-efficacy related to clinical reasoning;(4) raised awareness of personal cognitive biases. CONCLUSIONS: We found that explicitly teaching clinical reasoning theory and cognitive biases using an experiential learning model provides first-year medical students with valuable opportunities for developing knowledge, skills, and self-efficacy related to clinical reasoning.

The Fallacy of a Single Diagnosis.

BACKGROUND: Diagnostic reasoning requires clinicians to think through complex uncertainties. We tested the possibility of a bias toward an available single diagnosis in uncertain cases. DESIGN: We developed 5 different surveys providing a succinct description of a hypothetical individual patient scenaric. Each scenario was formulated in 2 versions randomized to participants, with the versions differing only in whether an alternative diagnosis was present or absent. The 5 scenarios were designed as separate tests of robustness using diverse cases, including a cautious scenario, a risky scenario, a sophisticated scenario, a validation scenario, and a comparative scenario (each survey containing only 1 version of 1 scenario). Participants included community members (n = 1104) and health care professionals (n = 200) who judged the chances of COVID infection in an individual patient. RESULTS: The first scenario described a cautious patient and found a 47% reduction in the estimated odds of COVID when a flu diagnosis was present compared with absent (odds ratio = 0.53, 95% confidence interval 0.30 to 0.94, P = 0.003). The second scenario described a less cautious patient and found a 70% reduction in the estimated odds of COVID in the presence of a flu diagnosis (odds ratio = 0.30, 95% confidence interval 0.13 to 0.70, P < 0.001). The third was a more sophisticated scenario presented to medical professionals and found a 73% reduction in the estimated odds of COVID in the presence of a mononucleosis diagnosis (odds ratio = 0.27, 95% confidence interval 0.10 to 0.75, P < 0.001). Two further scenarios-avoiding mention of population norms-replicated the results. LIMITATIONS: Brief hypothetical scenarios may overestimate the extent of bias in more complicated medical situations. CONCLUSIONS: These results demonstrate that an available simple diagnosis can lead individuals toward premature closure and a failure to fully consider additional severe diseases. HIGHLIGHTS: Occum's razor has been debated for centuries yet rarely subjected to experimental testing for evidence-based medicine.This article offers direct evidence that people favor an available simple diagnosis, thereby neglecting to consider additional serious diseases.The bias can lead individuals to mistakenly lower their judged likelihood of COVID or another disease when an alternate diagnosis is present.This misconception over the laws of probability appears in judgments by community members and by health care workers.The pitfall in reasoning extends to high-risk cases and is not easily attributed to information, incentives, or random chance.

Vaccination Against COVID-19: Human Behavior and Public Policy Analyzed from Behavioral Economics.

Society is facing a global pandemic, causing millions of deaths and hundreds of millions of infections. The importance of vaccination to face COVID-19 is decisive in the fight against the virus. However, many people have decided not to get vaccinated, ruining public health policy. The objective of this article is to apply knowledge about behavioral economics in the explanation of the behavior of those who decide not to be vaccinated, as well as the use of decision architecture and nudges for the design of behavioral interventions. The methodology used was qualitative, supported by bibliographic search and content analysis, with theoretical methods such as historical-logical analysis and deductive and hypothetical analysis. Behavioral economics has been used to modify behaviors associated with chronic non communicable diseases, so it can provide a solution to increase the number of people who are inoculated against the virus. The perception of risk and uncertainty, the amount of information and social pressure are identified as factors that influence the decision, as well as various heuristics and cognitive biases. The design of behavioral interventions should employ nudges in the decision architecture, starting from the "simple, attractive, social and timely" methodology as an opportunity to increase the number of people who are vaccinated. Copyright © 2022, Editorial Ciencias Medicas. All rights reserved.

Does outcome bias trump political tribalism?

Outcome bias occurs when people evaluate decision quality based on the outcome rather than the intentions of the decision maker. We replicate these findings and extend them to the realms of policy and politics. Approximately equal numbers of Republicans and Democrats judged policy decisions aimed at ameliorating the deleterious effects of the COVID-19 pandemic. We manipulated the affiliation of the decider (Republican vs. Democrat) and the aim of the policy (benefits health vs. benefits the economy;benefits health but hurts the economy vs. benefits the economy but hurts health). The results revealed that policy decisions aimed at addressing health problems or aimed at repairing the economy without negative externalities in other spheres of life were evaluated solely as a function of outcome in which successful outcomes generated significantly greater quality ratings than failures. However, judgments of policy decisions aimed at helping one sphere of life but hurting another (i.e., business closures) were qualified by significant interactions with the political party affiliation of the decision maker and that of the participant. Republicans' responses show evidence for outcome bias while favoring Republican deciders. In contrast, Democrats exhibited a greater degree of outcome bias while favoring decisions that prioritized health over the economy relative to decisions that prioritized the economy over health. (PsycInfo Database Record (c) 2023 APA, all rights reserved) Impact Statement What is the significance of this article for the general public?-Even though the COVID-19 pandemic is a health problem, a large proportion of people treated it as a political issue for which voters' political affiliation determined their response to the pandemic. Dealing effectively with the pandemic requires a unified response in a situation where health and the economy are frequently at loggerheads. Here we examined how voters think about policy decisions that aimed to address either public health or economic concerns stemming from the pandemic. In half of the cases, policies aimed at addressing one issue were detrimental to another. In general, people judge policy decisions as a function of their outcomes;however, they are more likely to be influenced by their political considerations when policies addressing one issue end up being detrimental to another. Specifically, Republicans' responses show evidence for outcome bias while favoring Republican deciders. In contrast, Democrats exhibited a greater degree of outcome bias while favoring decisions that prioritized health over the economy relative to decisions that prioritized the economy over health. (PsycInfo Database Record (c) 2023 APA, all rights reserved)

Attentional Bias for Sleep-Related Words as a Function of Severity of Insomnia Symptoms.

Attentional bias to sleep-related information is thought to be a core feature for developing and/or maintaining insomnia. This study used a hallmark measure of attentional bias, the dot-probe task, to determine whether this bias toward sleep-related stimuli was a function of the severity of insomnia symptoms. A sample of 231 volunteers (175 females; mean age of 26.91 ± 8.05 years) participated in this online study, filling out the Insomnia Severity Index (ISI) and performing a visual dot-probe task. After categorizing individuals based on the ISI score into normal, subclinical, and moderate/severe sleep groups, we only found a marginally significant interaction between sleep groups and the type of stimuli on RTs, suggesting that subclinical and moderate/severe sleep groups reported slower RTs for sleep-related words than for neutral words. When we calculated the attentional bias score (ABS), we found that ABS significantly differed from zero in the moderate/severe sleep group only, suggesting a disengagement for sleep-related information as a function of the severity of insomnia symptoms. This finding seems to suggest that insomnia is related to greater difficulties in shifting away from sleep-related stimuli.

Vaccination Against COVID-19: Human Behavior and Public Policy Analyzed from Behavioral Economics

Society is facing a global pandemic, causing millions of deaths and hundreds of millions of infections. The importance of vaccination to face COVID-19 is decisive in the fight against the virus. However, many people have decided not to get vaccinated, ruining public health policy. The objective of this article is to apply knowledge about behavioral economics in the explanation of the behavior of those who decide not to be vaccinated, as well as the use of decision architecture and nudges for the design of behavioral interventions. The methodology used was qualitative, supported by bibliographic search and content analysis, with theoretical methods such as historical-logical analysis and deductive and hypothetical analysis. Behavioral economics has been used to modify behaviors associated with chronic non communicable diseases, so it can provide a solution to increase the number of people who are inoculated against the virus. The perception of risk and uncertainty, the amount of information and social pressure are identified as factors that influence the decision, as well as various heuristics and cognitive biases. The design of behavioral interventions should employ nudges in the decision architecture, starting from the "simple, attractive, social and timely" methodology as an opportunity to increase the number of people who are vaccinated. Copyright © 2022, Editorial Ciencias Medicas. All rights reserved.